Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6720
    Prev
    Next
    INDEX
    Explanations

    references to color and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -0.95
    `,
    
    -0.92
    `;
    
    -0.87
    '));
    
    -0.84
    Geplaatst
    -0.79
    forChild
    -0.76
     оригіналу
    -0.76
    endpush
    -0.76
    ]]
    
    -0.76
    }\]
    -0.75
    POSITIVE LOGITS
     color
    3.62
     Color
    3.24
    color
    3.12
     colour
    3.06
    Color
    2.99
     COLOR
    2.99
     colors
    2.76
    COLOR
    2.66
     Colour
    2.64
    colour
    2.48
    Activations Density 0.107%

    No Known Activations